tangken333 commited on
Commit
0eb8c8c
·
verified ·
1 Parent(s): 996435b

End of training

Browse files
Files changed (5) hide show
  1. README.md +2 -1
  2. all_results.json +8 -0
  3. train_results.json +8 -0
  4. trainer_state.json +693 -0
  5. training_loss.png +0 -0
README.md CHANGED
@@ -4,6 +4,7 @@ license: apache-2.0
4
  base_model: Qwen/Qwen2.5-Coder-7B-Instruct
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: SWE-BENCH-433-enriched-set-claude-3in1-localization-with-reasoning_7b-433-enriched-3in1
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # SWE-BENCH-433-enriched-set-claude-3in1-localization-with-reasoning_7b-433-enriched-3in1
17
 
18
- This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) on an unknown dataset.
19
 
20
  ## Model description
21
 
 
4
  base_model: Qwen/Qwen2.5-Coder-7B-Instruct
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: SWE-BENCH-433-enriched-set-claude-3in1-localization-with-reasoning_7b-433-enriched-3in1
 
16
 
17
  # SWE-BENCH-433-enriched-set-claude-3in1-localization-with-reasoning_7b-433-enriched-3in1
18
 
19
+ This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) on the SWE-BENCH-433-enriched-set-claude-3in1-localization-with-reasoning dataset.
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.93048128342246,
3
+ "total_flos": 9.35169742560297e+16,
4
+ "train_loss": 0.686019714160632,
5
+ "train_runtime": 9873.9611,
6
+ "train_samples_per_second": 0.454,
7
+ "train_steps_per_second": 0.009
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.93048128342246,
3
+ "total_flos": 9.35169742560297e+16,
4
+ "train_loss": 0.686019714160632,
5
+ "train_runtime": 9873.9611,
6
+ "train_samples_per_second": 0.454,
7
+ "train_steps_per_second": 0.009
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,693 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.93048128342246,
5
+ "eval_steps": 500,
6
+ "global_step": 93,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03208556149732621,
13
+ "grad_norm": 0.20311123132705688,
14
+ "learning_rate": 1.0000000000000002e-06,
15
+ "loss": 1.0142,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.06417112299465241,
20
+ "grad_norm": 0.19597311317920685,
21
+ "learning_rate": 2.0000000000000003e-06,
22
+ "loss": 1.0111,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.0962566844919786,
27
+ "grad_norm": 0.19070063531398773,
28
+ "learning_rate": 3e-06,
29
+ "loss": 1.0203,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.12834224598930483,
34
+ "grad_norm": 0.19738665223121643,
35
+ "learning_rate": 4.000000000000001e-06,
36
+ "loss": 0.9815,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.16042780748663102,
41
+ "grad_norm": 0.1658538281917572,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.9497,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.1925133689839572,
48
+ "grad_norm": 0.13552631437778473,
49
+ "learning_rate": 6e-06,
50
+ "loss": 0.9655,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.22459893048128343,
55
+ "grad_norm": 0.12660366296768188,
56
+ "learning_rate": 7e-06,
57
+ "loss": 1.0031,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.25668449197860965,
62
+ "grad_norm": 0.13044770061969757,
63
+ "learning_rate": 8.000000000000001e-06,
64
+ "loss": 0.8836,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.2887700534759358,
69
+ "grad_norm": 0.133613720536232,
70
+ "learning_rate": 9e-06,
71
+ "loss": 0.904,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.32085561497326204,
76
+ "grad_norm": 0.13057634234428406,
77
+ "learning_rate": 1e-05,
78
+ "loss": 0.8347,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.35294117647058826,
83
+ "grad_norm": 0.15763278305530548,
84
+ "learning_rate": 9.996418774081658e-06,
85
+ "loss": 0.8767,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.3850267379679144,
90
+ "grad_norm": 0.13350480794906616,
91
+ "learning_rate": 9.985680226398261e-06,
92
+ "loss": 0.8649,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.41711229946524064,
97
+ "grad_norm": 0.11397632211446762,
98
+ "learning_rate": 9.967799739815925e-06,
99
+ "loss": 0.8318,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.44919786096256686,
104
+ "grad_norm": 0.09967950731515884,
105
+ "learning_rate": 9.942802927959444e-06,
106
+ "loss": 0.8099,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.48128342245989303,
111
+ "grad_norm": 0.09817608445882797,
112
+ "learning_rate": 9.910725598521014e-06,
113
+ "loss": 0.7997,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.5133689839572193,
118
+ "grad_norm": 0.09854481369256973,
119
+ "learning_rate": 9.871613701966067e-06,
120
+ "loss": 0.8052,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.5454545454545454,
125
+ "grad_norm": 0.09840090572834015,
126
+ "learning_rate": 9.825523265709667e-06,
127
+ "loss": 0.8383,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.5775401069518716,
132
+ "grad_norm": 0.08703222870826721,
133
+ "learning_rate": 9.772520313857777e-06,
134
+ "loss": 0.8014,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.6096256684491979,
139
+ "grad_norm": 0.07054264843463898,
140
+ "learning_rate": 9.712680772628365e-06,
141
+ "loss": 0.7716,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.6417112299465241,
146
+ "grad_norm": 0.07254040986299515,
147
+ "learning_rate": 9.646090361587828e-06,
148
+ "loss": 0.7857,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.6737967914438503,
153
+ "grad_norm": 0.06903552263975143,
154
+ "learning_rate": 9.572844470858537e-06,
155
+ "loss": 0.7589,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.7058823529411765,
160
+ "grad_norm": 0.08053260296583176,
161
+ "learning_rate": 9.493048024473413e-06,
162
+ "loss": 0.7776,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.7379679144385026,
167
+ "grad_norm": 0.07109075039625168,
168
+ "learning_rate": 9.406815330073244e-06,
169
+ "loss": 0.7594,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.7700534759358288,
174
+ "grad_norm": 0.06771097332239151,
175
+ "learning_rate": 9.314269915162115e-06,
176
+ "loss": 0.7548,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.8021390374331551,
181
+ "grad_norm": 0.06824363768100739,
182
+ "learning_rate": 9.215544350155423e-06,
183
+ "loss": 0.7432,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.8342245989304813,
188
+ "grad_norm": 0.06845725327730179,
189
+ "learning_rate": 9.110780058474052e-06,
190
+ "loss": 0.7391,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.8663101604278075,
195
+ "grad_norm": 0.06926020979881287,
196
+ "learning_rate": 9.000127113956673e-06,
197
+ "loss": 0.7673,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.8983957219251337,
202
+ "grad_norm": 0.06381599605083466,
203
+ "learning_rate": 8.883744025880429e-06,
204
+ "loss": 0.747,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.93048128342246,
209
+ "grad_norm": 0.06366810202598572,
210
+ "learning_rate": 8.761797511897907e-06,
211
+ "loss": 0.7633,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.9625668449197861,
216
+ "grad_norm": 0.05870290845632553,
217
+ "learning_rate": 8.634462259215719e-06,
218
+ "loss": 0.7426,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.9946524064171123,
223
+ "grad_norm": 0.06190042197704315,
224
+ "learning_rate": 8.501920674356755e-06,
225
+ "loss": 0.7761,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 1.0,
230
+ "grad_norm": 0.06190042197704315,
231
+ "learning_rate": 8.364362621864595e-06,
232
+ "loss": 0.7086,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 1.032085561497326,
237
+ "grad_norm": 0.1603803187608719,
238
+ "learning_rate": 8.221985152324385e-06,
239
+ "loss": 0.6956,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 1.0641711229946524,
244
+ "grad_norm": 0.06225842982530594,
245
+ "learning_rate": 8.07499222008977e-06,
246
+ "loss": 0.6742,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 1.0962566844919786,
251
+ "grad_norm": 0.055793747305870056,
252
+ "learning_rate": 7.923594391120237e-06,
253
+ "loss": 0.6592,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 1.1283422459893049,
258
+ "grad_norm": 0.05490822345018387,
259
+ "learning_rate": 7.768008541347423e-06,
260
+ "loss": 0.6395,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 1.160427807486631,
265
+ "grad_norm": 0.05545506253838539,
266
+ "learning_rate": 7.608457546002423e-06,
267
+ "loss": 0.6601,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 1.192513368983957,
272
+ "grad_norm": 0.05865738168358803,
273
+ "learning_rate": 7.445169960349167e-06,
274
+ "loss": 0.6438,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 1.2245989304812834,
279
+ "grad_norm": 0.05824247747659683,
280
+ "learning_rate": 7.278379692281209e-06,
281
+ "loss": 0.7292,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 1.2566844919786098,
286
+ "grad_norm": 0.055361997336149216,
287
+ "learning_rate": 7.10832566725092e-06,
288
+ "loss": 0.6213,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 1.2887700534759359,
293
+ "grad_norm": 0.0581163614988327,
294
+ "learning_rate": 6.9352514860110876e-06,
295
+ "loss": 0.6631,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 1.320855614973262,
300
+ "grad_norm": 0.05861780047416687,
301
+ "learning_rate": 6.759405075659165e-06,
302
+ "loss": 0.6472,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 1.3529411764705883,
307
+ "grad_norm": 0.06006443873047829,
308
+ "learning_rate": 6.58103833448412e-06,
309
+ "loss": 0.661,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 1.3850267379679144,
314
+ "grad_norm": 0.05911916866898537,
315
+ "learning_rate": 6.4004067711245366e-06,
316
+ "loss": 0.6537,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 1.4171122994652405,
321
+ "grad_norm": 0.05767710879445076,
322
+ "learning_rate": 6.2177691385549595e-06,
323
+ "loss": 0.6372,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 1.4491978609625669,
328
+ "grad_norm": 0.06271807849407196,
329
+ "learning_rate": 6.033387063424765e-06,
330
+ "loss": 0.6449,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 1.481283422459893,
335
+ "grad_norm": 0.05773553252220154,
336
+ "learning_rate": 5.8475246712804845e-06,
337
+ "loss": 0.6532,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 1.5133689839572193,
342
+ "grad_norm": 0.05972479656338692,
343
+ "learning_rate": 5.660448208208513e-06,
344
+ "loss": 0.639,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 1.5454545454545454,
349
+ "grad_norm": 0.060490116477012634,
350
+ "learning_rate": 5.472425659440157e-06,
351
+ "loss": 0.6427,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 1.5775401069518717,
356
+ "grad_norm": 0.056138068437576294,
357
+ "learning_rate": 5.2837263654653715e-06,
358
+ "loss": 0.6328,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 1.6096256684491979,
363
+ "grad_norm": 0.057874809950590134,
364
+ "learning_rate": 5.094620636205096e-06,
365
+ "loss": 0.6267,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 1.641711229946524,
370
+ "grad_norm": 0.1051662415266037,
371
+ "learning_rate": 4.905379363794907e-06,
372
+ "loss": 0.5955,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 1.6737967914438503,
377
+ "grad_norm": 0.05756345018744469,
378
+ "learning_rate": 4.71627363453463e-06,
379
+ "loss": 0.6069,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 1.7058823529411766,
384
+ "grad_norm": 0.059037283062934875,
385
+ "learning_rate": 4.527574340559844e-06,
386
+ "loss": 0.6352,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 1.7379679144385025,
391
+ "grad_norm": 0.06045999750494957,
392
+ "learning_rate": 4.33955179179149e-06,
393
+ "loss": 0.6434,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 1.7700534759358288,
398
+ "grad_norm": 0.05958287790417671,
399
+ "learning_rate": 4.152475328719517e-06,
400
+ "loss": 0.6803,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 1.8021390374331552,
405
+ "grad_norm": 0.05772184208035469,
406
+ "learning_rate": 3.966612936575235e-06,
407
+ "loss": 0.5837,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 1.8342245989304813,
412
+ "grad_norm": 0.05690668150782585,
413
+ "learning_rate": 3.782230861445041e-06,
414
+ "loss": 0.6416,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 1.8663101604278074,
419
+ "grad_norm": 0.055760458111763,
420
+ "learning_rate": 3.5995932288754655e-06,
421
+ "loss": 0.594,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 1.8983957219251337,
426
+ "grad_norm": 0.060565654188394547,
427
+ "learning_rate": 3.4189616655158803e-06,
428
+ "loss": 0.613,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 1.93048128342246,
433
+ "grad_norm": 0.0587182492017746,
434
+ "learning_rate": 3.240594924340835e-06,
435
+ "loss": 0.6263,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 1.962566844919786,
440
+ "grad_norm": 0.06040377542376518,
441
+ "learning_rate": 3.0647485139889145e-06,
442
+ "loss": 0.6344,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 1.9946524064171123,
447
+ "grad_norm": 0.05578358843922615,
448
+ "learning_rate": 2.89167433274908e-06,
449
+ "loss": 0.5962,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 2.0,
454
+ "grad_norm": 0.05578358843922615,
455
+ "learning_rate": 2.721620307718793e-06,
456
+ "loss": 0.6669,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 2.0320855614973263,
461
+ "grad_norm": 0.1518927663564682,
462
+ "learning_rate": 2.554830039650834e-06,
463
+ "loss": 0.5842,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 2.064171122994652,
468
+ "grad_norm": 0.05603505298495293,
469
+ "learning_rate": 2.391542453997578e-06,
470
+ "loss": 0.6017,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 2.0962566844919786,
475
+ "grad_norm": 0.0569174662232399,
476
+ "learning_rate": 2.2319914586525776e-06,
477
+ "loss": 0.5905,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 2.128342245989305,
482
+ "grad_norm": 0.05474628135561943,
483
+ "learning_rate": 2.0764056088797646e-06,
484
+ "loss": 0.5657,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 2.160427807486631,
489
+ "grad_norm": 0.05412266403436661,
490
+ "learning_rate": 1.9250077799102323e-06,
491
+ "loss": 0.5692,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 2.192513368983957,
496
+ "grad_norm": 0.05691121146082878,
497
+ "learning_rate": 1.7780148476756148e-06,
498
+ "loss": 0.5528,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 2.2245989304812834,
503
+ "grad_norm": 0.0541236586868763,
504
+ "learning_rate": 1.6356373781354058e-06,
505
+ "loss": 0.5426,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 2.2566844919786098,
510
+ "grad_norm": 0.054437655955553055,
511
+ "learning_rate": 1.4980793256432474e-06,
512
+ "loss": 0.5578,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 2.2887700534759357,
517
+ "grad_norm": 0.0597856268286705,
518
+ "learning_rate": 1.3655377407842813e-06,
519
+ "loss": 0.5612,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 2.320855614973262,
524
+ "grad_norm": 0.060152262449264526,
525
+ "learning_rate": 1.2382024881020937e-06,
526
+ "loss": 0.5616,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 2.3529411764705883,
531
+ "grad_norm": 0.05507192015647888,
532
+ "learning_rate": 1.1162559741195733e-06,
533
+ "loss": 0.5736,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 2.385026737967914,
538
+ "grad_norm": 0.0576910674571991,
539
+ "learning_rate": 9.998728860433277e-07,
540
+ "loss": 0.5565,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 2.4171122994652405,
545
+ "grad_norm": 0.056697096675634384,
546
+ "learning_rate": 8.892199415259501e-07,
547
+ "loss": 0.5509,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 2.449197860962567,
552
+ "grad_norm": 0.05489673465490341,
553
+ "learning_rate": 7.844556498445788e-07,
554
+ "loss": 0.5783,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 2.481283422459893,
559
+ "grad_norm": 0.05427519232034683,
560
+ "learning_rate": 6.857300848378857e-07,
561
+ "loss": 0.553,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 2.5133689839572195,
566
+ "grad_norm": 0.05728753283619881,
567
+ "learning_rate": 5.931846699267558e-07,
568
+ "loss": 0.5956,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 2.5454545454545454,
573
+ "grad_norm": 0.05481986328959465,
574
+ "learning_rate": 5.0695197552659e-07,
575
+ "loss": 0.564,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 2.5775401069518717,
580
+ "grad_norm": 0.05629381909966469,
581
+ "learning_rate": 4.271555291414636e-07,
582
+ "loss": 0.5545,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 2.6096256684491976,
587
+ "grad_norm": 0.057915519922971725,
588
+ "learning_rate": 3.539096384121743e-07,
589
+ "loss": 0.5994,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 2.641711229946524,
594
+ "grad_norm": 0.05390770733356476,
595
+ "learning_rate": 2.873192273716369e-07,
596
+ "loss": 0.5615,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 2.6737967914438503,
601
+ "grad_norm": 0.056489136070013046,
602
+ "learning_rate": 2.274796861422246e-07,
603
+ "loss": 0.5494,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 2.7058823529411766,
608
+ "grad_norm": 0.05273538455367088,
609
+ "learning_rate": 1.7447673429033361e-07,
610
+ "loss": 0.5975,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 2.7379679144385025,
615
+ "grad_norm": 0.05448044836521149,
616
+ "learning_rate": 1.2838629803393343e-07,
617
+ "loss": 0.5877,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 2.770053475935829,
622
+ "grad_norm": 0.05841987207531929,
623
+ "learning_rate": 8.927440147898703e-08,
624
+ "loss": 0.5497,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 2.802139037433155,
629
+ "grad_norm": 0.053782325237989426,
630
+ "learning_rate": 5.7197072040557356e-08,
631
+ "loss": 0.552,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 2.834224598930481,
636
+ "grad_norm": 0.05557689070701599,
637
+ "learning_rate": 3.220026018407541e-08,
638
+ "loss": 0.5543,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 2.8663101604278074,
643
+ "grad_norm": 0.055889178067445755,
644
+ "learning_rate": 1.431977360173975e-08,
645
+ "loss": 0.5606,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 2.8983957219251337,
650
+ "grad_norm": 0.058224692940711975,
651
+ "learning_rate": 3.5812259183426457e-09,
652
+ "loss": 0.5859,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 2.93048128342246,
657
+ "grad_norm": 0.06218594312667847,
658
+ "learning_rate": 0.0,
659
+ "loss": 0.5555,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 2.93048128342246,
664
+ "step": 93,
665
+ "total_flos": 9.35169742560297e+16,
666
+ "train_loss": 0.686019714160632,
667
+ "train_runtime": 9873.9611,
668
+ "train_samples_per_second": 0.454,
669
+ "train_steps_per_second": 0.009
670
+ }
671
+ ],
672
+ "logging_steps": 1,
673
+ "max_steps": 93,
674
+ "num_input_tokens_seen": 0,
675
+ "num_train_epochs": 3,
676
+ "save_steps": 200,
677
+ "stateful_callbacks": {
678
+ "TrainerControl": {
679
+ "args": {
680
+ "should_epoch_stop": false,
681
+ "should_evaluate": false,
682
+ "should_log": false,
683
+ "should_save": true,
684
+ "should_training_stop": true
685
+ },
686
+ "attributes": {}
687
+ }
688
+ },
689
+ "total_flos": 9.35169742560297e+16,
690
+ "train_batch_size": 1,
691
+ "trial_name": null,
692
+ "trial_params": null
693
+ }
training_loss.png ADDED